#11: Sequential and Active Decision Making: Bandit Theory by Prof. A. Carpentier

Join our free BLISS Speaker Series!

We are excited to feature Prof. Alexandra Carpentier, Professor at the University of Potsdam and Chair of Mathematical Statistics and Machine Learning, who will discuss Sequential and Active Decision Making: Bandit Theory, lasting approximately 45 minutes. After the talk, seize the opportunity to connect with fellow AI enthusiasts to share ideas and questions while enjoying drinks and [special event!] freshly baked waffles. Door close by 7.15pm, so please come early! Also, "attend"ing (RSVP) here on Meetup is strictly necessary to be guaranteed entry.

Abstract:
This talk introduces Bandit Theory, a framework for sequential, adaptive learning in uncertain environments with partial information. Inspired by the classic multi-armed bandit problem, where a decision-maker balances exploration and exploitation, this approach extends to settings where actions actively influence the data received. Unlike traditional batch learning, the learner gathers data incrementally, adapting strategies based on observations.
The goals are twofold: (1) to deepen understanding of the system being studied and (2) to achieve specific objectives defined by application needs. For example, in attention detection using eye tracking, a system identifies poorly attended screen regions by probing user responses and refining its strategy. These methods showcase the power of bandit-inspired learning in dynamic, interactive applications.

About the Speaker:
Professor Alexandra Carpentier is a Professor of Mathematical Statistics and Machine Learning at the University of Potsdam. She holds a PhD in Mathematical Statistics from INRIA, was a Postdoctoral Researcher at the University of Cambridge and has previously been on faculty at the University of Magdeburg and Université Paris-Nanterre. Her research focuses on sequential decision-making, bandit algorithms, and high-dimensional statistical inference, with applications in machine learning, anomaly detection, and neuroscience.
She is the recipient of the prestigious Von Kaven Prize (2020) and serves as an associate editor for several top journals, including the Annals of Statistics and SIAM UQ.

About us:
We are BLISS e.V., a student organisation in Berlin that connects like-minded individuals who share great interest and passion for the field of machine learning. This winter semester (2024/25), we will again host an exciting speaker series on site in Berlin, featuring excellent researchers from TU Berlin, Mantis Analytics, HU Berlin, InstaDeep, FU Berlin, SakanaAI, University of Potsdam and University of Magdeburg. Besides, we also have a weekly reading group and biweekly community events!

Website: https://bliss.berlin
Youtube: https://www.youtube.com/@bliss.ev.berlin

Disclaimer: By attending this event you agree to be photographed.